© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46579
    Prev
    Next
    INDEX
    Explanations

    is someone asking a question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ariat
    -0.08
    arth
    -0.08
    atars
    -0.08
    statt
    -0.08
     Mandal
    -0.07
    vie
    -0.07
    ater
    -0.07
     familiar
    -0.07
     https
    -0.07
    Ø
    -0.07
    POSITIVE LOGITS
    ifies
    0.13
     Cruise
    0.10
    abe
    0.10
    ows
    0.10
     BG
    0.10
     Painter
    0.09
    .requires
    0.09
     anyone
    0.09
    æıIJ示
    0.09
     espera
    0.09
    Activations Density 0.087%

    No Known Activations